Name: pre-push-check
Rating: 54.400000000000006 (1 reviews)
Author: AndreJorgeLopes

Blog Docs Log in Get started

pre-push-check

Run the full pre-push review pipeline — code review checks, self-review against CLAUDE.md, and a final report.

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./devflow-plugin/skills/pre-push-check/SKILL.md

The canonical home for this skill is pre-push-check in AndreJorgeLopes/devflow

Quality

Content

68%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill body is concise and actionable with a clear sequenced workflow and a ready-to-use report template, but it lacks an explicit validation gate before the final push verdict, which the rubric requires for batch/destructive operations. Adding a verify-then-proceed checkpoint would lift workflow clarity.

Suggestions

Insert an explicit validation checkpoint in step 6, e.g. 'Only mark READY TO PUSH when all code-review checks PASS and no CLAUDE.md compliance item is FAIL; otherwise list fixes and re-run devflow check after remediation.'

Give the exact command for deriving the branch name and commit count (e.g. `git rev-parse --abbrev-ref HEAD` and `git rev-list --count origin/HEAD..HEAD`) so the report fields are fully executable.

Clarify the fallback trigger condition for `devflow check` (how to detect neither CLI is available) so Claude can branch deterministically rather than by judgment.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient and assumes Claude's competence, with only minor padding (e.g. the explanatory aside on devflow's CLIs in step 2); it does not explain concepts Claude already knows.	4 / 5
Actionability	It provides concrete, executable commands (`git diff --stat`, `devflow check`, `yarn lint`) and a copy-paste report template, with minor gaps such as the exact branch-name command being implied rather than given.	4 / 5
Workflow Clarity	Steps are clearly sequenced, but this is a batch/destructive-adjacent operation (pushing code) that lacks an explicit validation checkpoint confirming checks passed before declaring 'safe to push'; the rubric caps such skills at 3 without validation feedback loops.	3 / 5
Progressive Disclosure	Content is well organized into clearly signaled sections (Steps, report template) with no bundle files to misplace; for a self-contained single-file skill this is good structure with only minor organization gaps.	4 / 5
	Total	15 / 20 Passed

Description

51%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly states what the skill does and is reasonably specific, but it omits an explicit 'Use when...' trigger clause and relies on one somewhat technical phrase rather than natural user keywords. Adding concrete trigger phrases would lift the completeness and trigger-term scores.

Suggestions

Append an explicit trigger clause, e.g. 'Use when about to push code, before running git push, or when the user asks for a pre-push review.'

Add natural synonyms a user might say, such as 'review my changes before pushing' or 'pre-push checks', to improve trigger-term coverage.

Tighten third-person voice consistency and consider naming the concrete checks (lint, type-check, scope discipline) to push specificity toward 5.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete actions ('code review checks', 'self-review against CLAUDE.md', 'a final report'), but the actions are high-level process steps rather than fully enumerated capabilities, leaving minor coverage gaps.	4 / 5
Completeness	It has a clear 'what' (run the pre-push review pipeline and its components) but no explicit 'Use when...' trigger clause, so per the rubric a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	It mentions 'pre-push review pipeline' but lacks natural phrases a user would say (e.g. 'before pushing', 'review my changes'), and includes no synonyms or trigger variants.	2 / 5
Distinctiveness Conflict Risk	'Pre-push review pipeline' is a fairly distinct niche tied to a specific git workflow, with only minor overlap risk against generic code-review skills.	4 / 5
	Total	13 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: AndreJorgeLopes/devflow
Path: devflow-plugin/skills/pre-push-check/SKILL.md
Commit: bd4b70c

Reviewed: 17 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.